LICENSE
README.md
pyproject.toml
src/agent_inspect/__init__.py
src/agent_inspect/clients/__init__.py
src/agent_inspect/clients/azure_openai_client.py
src/agent_inspect/clients/llm_client.py
src/agent_inspect/core/utils.py
src/agent_inspect/exception/__init__.py
src/agent_inspect/exception/error_codes.py
src/agent_inspect/exception/exception.py
src/agent_inspect/metrics/__init__.py
src/agent_inspect/metrics/constants.py
src/agent_inspect/metrics/adapters/__init__.py
src/agent_inspect/metrics/adapters/base_adapter.py
src/agent_inspect/metrics/adapters/tau2bench_adapter.py
src/agent_inspect/metrics/adapters/toolsandbox_adapter.py
src/agent_inspect/metrics/multi_samples/__init__.py
src/agent_inspect/metrics/multi_samples/multi_sample_metric.py
src/agent_inspect/metrics/multi_samples/pass_at_k.py
src/agent_inspect/metrics/multi_samples/pass_hat_k.py
src/agent_inspect/metrics/observed/__init__.py
src/agent_inspect/metrics/observed/latency.py
src/agent_inspect/metrics/observed/observed_metric.py
src/agent_inspect/metrics/observed/token_count.py
src/agent_inspect/metrics/observed/tool_call_count.py
src/agent_inspect/metrics/scorer/__init__.py
src/agent_inspect/metrics/scorer/auc.py
src/agent_inspect/metrics/scorer/llm_based_metric.py
src/agent_inspect/metrics/scorer/metric.py
src/agent_inspect/metrics/scorer/ppt.py
src/agent_inspect/metrics/scorer/progress.py
src/agent_inspect/metrics/scorer/success.py
src/agent_inspect/metrics/scorer/templates.py
src/agent_inspect/metrics/scorer/tool_correctness.py
src/agent_inspect/metrics/utils/__init__.py
src/agent_inspect/metrics/utils/expected_tool_validators.py
src/agent_inspect/metrics/utils/subgoal_validators.py
src/agent_inspect/metrics/utils/trace_validators.py
src/agent_inspect/metrics/validator/__init__.py
src/agent_inspect/metrics/validator/constants.py
src/agent_inspect/metrics/validator/exact_match.py
src/agent_inspect/metrics/validator/llm_check.py
src/agent_inspect/metrics/validator/regex_match.py
src/agent_inspect/metrics/validator/subgoal_completion.py
src/agent_inspect/metrics/validator/templates.py
src/agent_inspect/metrics/validator/tool_call_completion.py
src/agent_inspect/metrics/validator/validator.py
src/agent_inspect/models/__init__.py
src/agent_inspect/models/llm_payload.py
src/agent_inspect/models/llm_response.py
src/agent_inspect/models/metrics/__init__.py
src/agent_inspect/models/metrics/agent_data_sample.py
src/agent_inspect/models/metrics/agent_trace.py
src/agent_inspect/models/metrics/metric_score.py
src/agent_inspect/models/metrics/validation_result.py
src/agent_inspect/models/tools/__init__.py
src/agent_inspect/models/tools/analysis_models.py
src/agent_inspect/models/tools/error_cluster.py
src/agent_inspect/models/user_proxy/__init__.py
src/agent_inspect/models/user_proxy/chat.py
src/agent_inspect/models/user_proxy/terminating_condition.py
src/agent_inspect/tools/__init__.py
src/agent_inspect/tools/utils.py
src/agent_inspect/tools/error_analysis/__init__.py
src/agent_inspect/tools/error_analysis/base_error_analysis.py
src/agent_inspect/tools/error_analysis/deterministic_tool_call_error_analysis.py
src/agent_inspect/tools/error_analysis/llm_output_schemas.py
src/agent_inspect/tools/error_analysis/llm_templates.py
src/agent_inspect/tools/error_analysis/semisupervised_subgoal_error_analysis.py
src/agent_inspect/tools/error_analysis/semisupervised_tool_call_error_analysis.py
src/agent_inspect/tools/error_analysis/statistic_analysis.py
src/agent_inspect/tools/error_analysis/subgoal_error_analysis.py
src/agent_inspect/tools/error_analysis/tool_call_error_analysis.py
src/agent_inspect/tools/error_analysis/unsupervised_subgoal_error_analysis.py
src/agent_inspect/tools/error_analysis/utils/validator.py
src/agent_inspect/user_proxy/__init__.py
src/agent_inspect/user_proxy/constants.py
src/agent_inspect/user_proxy/llm_proxy_agent.py
src/agent_inspect/user_proxy/templates.py
src/agent_inspect/user_proxy/user_proxy_agent.py
src/agent_inspect/user_proxy/utils/__init__.py
src/agent_inspect/user_proxy/utils/user_proxy_validators.py
src/agent_inspect/utils/auc_calculator.py
src/agent_quality_inspect.egg-info/PKG-INFO
src/agent_quality_inspect.egg-info/SOURCES.txt
src/agent_quality_inspect.egg-info/dependency_links.txt
src/agent_quality_inspect.egg-info/requires.txt
src/agent_quality_inspect.egg-info/top_level.txt
tests/test_adapters.py
tests/test_aggregator.py
tests/test_auc.py
tests/test_auc_calculator.py
tests/test_azure_openai_client.py
tests/test_exact_match.py
tests/test_latency.py
tests/test_llm_check.py
tests/test_pass_at_k.py
tests/test_pass_hat_k.py
tests/test_ppt.py
tests/test_progress.py
tests/test_regex_match.py
tests/test_statistic_analysis.py
tests/test_subgoal_completion.py
tests/test_subgoal_validator.py
tests/test_success.py
tests/test_token_count.py
tests/test_tooL_call_completion.py
tests/test_tool_call_correctness.py
tests/test_tool_call_count.py
tests/test_trace_validators.py
tests/test_validate_subgoal.py